Supporting and Performing Culture from the Inside

Lea Frermann; Steven Bird

cs.CLSep 26, 2026

Supporting and Performing Culture from the Inside

Authors: Lea Frermann, Steven Bird

Organizations: The University of Tübingen, Tübingen, Germany · The University of Melbourne, Melbourne, Australia · Charles Darwin University, Darwin, Australia

Abstract

Anthropology and related disciplines which study culture have often found it useful to consider their epistemological and methodological approaches in terms of emic versus etic. This is the distinction between the insider perspective, how the world is viewed by a member of the culture, versus the outsider perspective, the scientific cataloguing of cultural knowledge and practice. We adopt this framework to systematically analyse assumptions in recent research on culture in NLP along the full pipeline of task selection, data collection, system design and evaluation. We draw attention to the `culture of NLP' which shapes the research focus and approaches of our field, and suggest pathways towards a more culturally attuned AI.

Figures & tables

Figure 1: Hall’s Cultural Iceberg: forms and behaviours (etic) can be observed by outsiders, while corresponding meanings and beliefs (emic) are only accessible to insiders ( Hall, 1976 , after) .

	Task	Data	System Design	Deployment / Evaluation
Etic	generic solns to external problems	data extraction for LLMs	simulate or improve on humans	efficiency and scalability
Etic	$\triangleright$ generate facts about any culture	$\triangleright$ translated or synthesized common sense benchmarks	$\triangleright$ text chat; adapting to user language; flexibility in tone/register	$\triangleright$ correctness and completeness of responses
Emic	local agency in shaping their world, identifying problems, exploring solutions	elicit cultural concepts and logics	build / augment human capacity in sustaining cultural vitality	local decision making, maintaining culture and locally meaningful livelihoods
	$\triangleright$ understanding western concepts which have no translation (e.g. “risk”)	$\triangleright$ exegesis of western cultural concepts into local languages	$\triangleright$ redesign of text interaction to follow local teacher-led pattern	$\triangleright$ equipped with actionable information, people make better-informed choices
	$\triangleright$ transmitting knowledge practices (e.g. food collection/preparation)	$\triangleright$ videos of people demonstrating knowledge practices, sharing lore	$\triangleright$ collection management and navigation, spoken term retrieval	$\triangleright$ measure user-reported utility and safety

Table 1: Etic vs Emic Perspectives on Four Stages of AI Development

Appendix figures & tables3 assets

Supplementary material from the paper’s appendix.

Appendix

Category	N	$\mathbf{\%}$
Resource	50	0.467
Survey	8	0.075
Analysis	15	0.140
Method	31	0.290

Appendix

Table A.1: Distribution over main contributions in papers in our survey.

Category	N	$\mathbf{\%}$
Assess / augment cultural knowledge in LLMs	78	0.729

Appendix

Table A.2: Fraction of paper with a focus on assessing or augmenting cultural knowledge in LLMs.

Category	N	$\mathbf{\%}$
culture annotators	19	0.178
broad data	41	0.383
synthetic	33	0.308
translation	3	0.028
– / LLM output analysis	4	0.037
– / survey	8	0.075

Appendix

Table A.3: Distribution over data set creation approaches in the papers in our survey. Papers of the last two categories were not included, as they did not contribute data sets or investigated culture in LLM output (rather than human artifacts).

Cultural Alignment

Cultural alignment studies how AI systems represent and respond to the values, norms, languages, and lived contexts of different communities.

See all 46 papers

Plurification in/of language technology -- The integration of culture in next-generation AI
Jun 20, 2026Gertraud Koch, Fausto GiunchigliaCultural Alignment Cultural Bias in Language Models
University of Hamburg, Edmund-Siemers-Allee 1 West, Germany · University of Trento, Dipartimento Ingegneria e Scienza dell'Informazione
Language Models as Measurement Apparatus for Culture
Jul 2, 2026Kent K. Chang
School of Information University of California, Berkeley
CultureMINE: Datasets and Methods for Improving the Cultural Capabilities of NLP Systems
Sep 18, 2026Tania Chakraborty, Eylon Caplan, Zhaoqing Wu +4Cultural Knowledge in Language Models
Purdue University · University of Pennsylvania

Jun 20, 2026J/K move · Enter open · S save

Plurification in/of language technology -- The integration of culture in next-generation AI

Gertraud Koch, Fausto Giunchiglia

University of Hamburg, Edmund-Siemers-Allee 1 West, Germany · University of Trento, Dipartimento Ingegneria e Scienza dell'Informazione

Cultural Alignment Cultural Bias in Language Models

Open paper AskPDF arXiv

The paper explores how "culture" can be operationalised in Natural Language Processing (NLP) and what this reveals about the possibilities and limits of considering a plurality of cultural backgrounds in technological design. It proposes that cultural alignment cannot be achieved only by adding more examples of "other cultures", rather it requires plural epistemologies: allowing multiple, locally grounded ways of knowing. To analyze how this plurality of knowing can be addressed in NLP, the paper uses a socio-technical model of language technology (LT) design, the five layers of technological activity model, for collecting and systematizing approaches to culture in NLP. The analysis shows that while NLP research has made progress toward more culturally sensitive systems, many approaches remain partial, addressing "culture" primarily at the level of output or representation while leaving deeper questions of power, governance, and social context unresolved. The paper concludes that operationalising culture requires much more than technical adaptation; it suggests a reflexive and plural socio-technical approach that navigates potentials and limits of computational formalisation for accounting multiple linguistic and socio-cultural backgrounds.

Abstract

Cultural Alignment

Explore similar work

Plurification in/of language technology -- The integration of culture in next-generation AI

Language Models as Measurement Apparatus for Culture

CultureMINE: Datasets and Methods for Improving the Cultural Capabilities of NLP Systems